Loading...
conference paper
Learning Vision-Based Quadrotor Control in User Proximity
March 25, 2019
2019 14th ACM/IEEE International Conference on Human-Robot Interaction (HRI)
We consider a quadrotor equipped with a forward-facing camera, and an user freely moving in its proximity; we control the quadrotor in order to stay in front of the user, using only camera frames. To do so, we train a deep neural network to predict the drone controls given the camera image. Training data is acquired by running a simple hand-designed controller which relies on optical motion tracking data.
Type
conference paper
Authors
Mantegazza, Dario
•
Guzzi, Jerome
•
Gambardella, Luca M.
•
Giusti, Alessandro
Publication date
2019-03-25
Published in
2019 14th ACM/IEEE International Conference on Human-Robot Interaction (HRI)
Start page
369
End page
369
Peer reviewed
REVIEWED
EPFL units
Event name | Event place | Event date |
Daegu, Korea (South) | March 11-14, 2019 | |
Available on Infoscience
October 31, 2019
Use this identifier to reference this record